Tài liệu Bài giảng introduction to computer vision

Chapter 1 - Introduction 1-1 Chapter 1 Introduction to Computer Vision James Hays, Brown University Department of Mechatronics Chapter 1 - Introduction 1-2 Contents • • • • • Introductions What is Computer Vision? Why study computer vision? Why computer vision matters? How vision is used now? Department of Mechatronics 1-3 Chapter 1 - Introduction Brief history of computer vision • 1966: Minsky assigns computer vision as an undergrad summer project • 1960’s: interpretation of synthetic worlds • 1970’s: some progress on interpreting selected images • 1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor • 1990’s: face recognition; statistical analysis in vogue • 2000’s: broader recognition; large annotated datasets available; video processing starts • 2030’s: robot uprising? Department of Mechatronics Guzman ‘68 Ohta Kanade ‘78 Turk and Pentland ‘91 Chapter 1 - Introduction 1-4 Computer Vision • Make computers understand images and video. What kind of scene? Where are the cars? How far is the building? Department of Mechatronics Chapter 1 - Introduction 1-5 What is (computer) vision? Human brain: ~100 ÷ 1.000 trillion synapses (Artificial) Neural network: ~1 ÷ 10 billion synapses Human brains have ~10.000 computational power than computer brains Lex Fridman, MIT Department of Mechatronics Chapter 1 - Introduction 1-6 Computer Vision and Nearby Fields • Computer Graphics: Models to Images • Computer Photography: Images to Images • Computer Vision: Images to Models Department of Mechatronics Chapter 1 - Introduction 1-7 Related disciplines Department of Mechatronics Chapter 1 - Introduction 1-8 What is it related to? Department of Mechatronics Chapter 1 - Introduction 1-9 The goal of computer vision • To bridge the gap between pixels and “meaning”. What we see Department of Mechatronics What a computer sees 1-10 Department of Mechatronics Chapter 1 - Introduction Chapter 1 - Introduction 1-11 Segmentation Department of Mechatronics Chapter 1 - Introduction 1-12 Perception Department of Mechatronics 1-13 Department of Mechatronics Chapter 1 - Introduction 1-14 Department of Mechatronics Chapter 1 - Introduction Chapter 1 - Introduction 1-15 What kind of information can we extract from an image? • Metric 3D information • Sematic information Department of Mechatronics Chapter 1 - Introduction 1-16 Guess which bread is real? Department of Mechatronics Chapter 1 - Introduction 1-17 Left one is real Department of Mechatronics Chapter 1 - Introduction 1-18 Vision as measurement device Department of Mechatronics 1-19 Chapter 1 - Introduction Vision as a source of sematic information Department of Mechatronics Chapter 1 - Introduction 1-20 Why study computer vision? • Vision is useful: images and video are everywhere. Department of Mechatronics